{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F2DGDBORF5HIAKR4D2DJS6FE2F","short_pith_number":"pith:F2DGDBOR","canonical_record":{"source":{"id":"2408.05456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-10T06:35:11Z","cross_cats_sorted":[],"title_canon_sha256":"6e0803dbcde8d207f2d692d6ee1b239fc6cb499f220a7c7dc11d497319250b79","abstract_canon_sha256":"2eebddb3799437e87dc4cd7a3fd33db1978efa6a96b7cf21569235010e57b705"},"schema_version":"1.0"},"canonical_sha256":"2e866185d12f4e802a3c1e869978a4d153d2e3d240ac1f48fa6c9b8472fa2daf","source":{"kind":"arxiv","id":"2408.05456","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05456","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05456v2","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05456","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"pith_short_12","alias_value":"F2DGDBORF5HI","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"pith_short_16","alias_value":"F2DGDBORF5HIAKR4","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"pith_short_8","alias_value":"F2DGDBOR","created_at":"2026-07-05T11:47:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F2DGDBORF5HIAKR4D2DJS6FE2F","target":"record","payload":{"canonical_record":{"source":{"id":"2408.05456","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-10T06:35:11Z","cross_cats_sorted":[],"title_canon_sha256":"6e0803dbcde8d207f2d692d6ee1b239fc6cb499f220a7c7dc11d497319250b79","abstract_canon_sha256":"2eebddb3799437e87dc4cd7a3fd33db1978efa6a96b7cf21569235010e57b705"},"schema_version":"1.0"},"canonical_sha256":"2e866185d12f4e802a3c1e869978a4d153d2e3d240ac1f48fa6c9b8472fa2daf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:13.022479Z","signature_b64":"l0jOrJtTmTAUZjGspoR92Ij0tccE68nAsLL4Aqxv/dHYLO8VyNTK3M15rNkMnjbhST+M2zObl+0gVYzaYaI+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e866185d12f4e802a3c1e869978a4d153d2e3d240ac1f48fa6c9b8472fa2daf","last_reissued_at":"2026-07-05T11:47:13.021918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:13.021918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.05456","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:47:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kwaecSa6HZijvYg+CbZp8GOpLYle1bKCrmIs0QF4wE1unx04eyjQcd4mTwr9h4oVJ3dRPsozQxpGuEXeIY4vAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:17:35.554557Z"},"content_sha256":"c4cadeafec71c05fce51b062c2439e73f3070ff1e081e413f627419a9482fb4a","schema_version":"1.0","event_id":"sha256:c4cadeafec71c05fce51b062c2439e73f3070ff1e081e413f627419a9482fb4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F2DGDBORF5HIAKR4D2DJS6FE2F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Wenbo Shang, Xin Huang, Xuliang Zhu","submitted_at":"2024-08-10T06:35:11Z","abstract_excerpt":"Unified graph representation learning aims to generate node embeddings, which can be applied to multiple downstream applications of graph analytics. However, existing studies based on graph neural networks and language models either suffer from the limitations of numerous training needs toward specific downstream predictions, poor generalization, or shallow semantic features. In this work, we propose a novel Path-LLM model to efficiently learn unified graph representation, which leverages a powerful large language model (LLM) to incorporate our proposed path features. Our Path-LLM framework co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05456","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.05456/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:47:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TbOM4alA7c42KnJgcFp21bCBZnS7z5pWuKk9oJABcOyyz5Nb3d1Z3m1H3g7h/htQWeWNHWVjdTQbe6drdC5uBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:17:35.554997Z"},"content_sha256":"0c5e3b4057b7b294333aa007e9fa81d478e395677bd12ddccce5b272921a811f","schema_version":"1.0","event_id":"sha256:0c5e3b4057b7b294333aa007e9fa81d478e395677bd12ddccce5b272921a811f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F2DGDBORF5HIAKR4D2DJS6FE2F/bundle.json","state_url":"https://pith.science/pith/F2DGDBORF5HIAKR4D2DJS6FE2F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F2DGDBORF5HIAKR4D2DJS6FE2F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T21:17:35Z","links":{"resolver":"https://pith.science/pith/F2DGDBORF5HIAKR4D2DJS6FE2F","bundle":"https://pith.science/pith/F2DGDBORF5HIAKR4D2DJS6FE2F/bundle.json","state":"https://pith.science/pith/F2DGDBORF5HIAKR4D2DJS6FE2F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F2DGDBORF5HIAKR4D2DJS6FE2F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F2DGDBORF5HIAKR4D2DJS6FE2F","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2eebddb3799437e87dc4cd7a3fd33db1978efa6a96b7cf21569235010e57b705","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-10T06:35:11Z","title_canon_sha256":"6e0803dbcde8d207f2d692d6ee1b239fc6cb499f220a7c7dc11d497319250b79"},"schema_version":"1.0","source":{"id":"2408.05456","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05456","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05456v2","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05456","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"pith_short_12","alias_value":"F2DGDBORF5HI","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"pith_short_16","alias_value":"F2DGDBORF5HIAKR4","created_at":"2026-07-05T11:47:13Z"},{"alias_kind":"pith_short_8","alias_value":"F2DGDBOR","created_at":"2026-07-05T11:47:13Z"}],"graph_snapshots":[{"event_id":"sha256:0c5e3b4057b7b294333aa007e9fa81d478e395677bd12ddccce5b272921a811f","target":"graph","created_at":"2026-07-05T11:47:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.05456/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unified graph representation learning aims to generate node embeddings, which can be applied to multiple downstream applications of graph analytics. However, existing studies based on graph neural networks and language models either suffer from the limitations of numerous training needs toward specific downstream predictions, poor generalization, or shallow semantic features. In this work, we propose a novel Path-LLM model to efficiently learn unified graph representation, which leverages a powerful large language model (LLM) to incorporate our proposed path features. Our Path-LLM framework co","authors_text":"Wenbo Shang, Xin Huang, Xuliang Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-10T06:35:11Z","title":"Path-LLM: A Shortest-Path-based LLM Learning for Unified Graph Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05456","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c4cadeafec71c05fce51b062c2439e73f3070ff1e081e413f627419a9482fb4a","target":"record","created_at":"2026-07-05T11:47:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2eebddb3799437e87dc4cd7a3fd33db1978efa6a96b7cf21569235010e57b705","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-10T06:35:11Z","title_canon_sha256":"6e0803dbcde8d207f2d692d6ee1b239fc6cb499f220a7c7dc11d497319250b79"},"schema_version":"1.0","source":{"id":"2408.05456","kind":"arxiv","version":2}},"canonical_sha256":"2e866185d12f4e802a3c1e869978a4d153d2e3d240ac1f48fa6c9b8472fa2daf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e866185d12f4e802a3c1e869978a4d153d2e3d240ac1f48fa6c9b8472fa2daf","first_computed_at":"2026-07-05T11:47:13.021918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:13.021918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l0jOrJtTmTAUZjGspoR92Ij0tccE68nAsLL4Aqxv/dHYLO8VyNTK3M15rNkMnjbhST+M2zObl+0gVYzaYaI+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:13.022479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05456","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c4cadeafec71c05fce51b062c2439e73f3070ff1e081e413f627419a9482fb4a","sha256:0c5e3b4057b7b294333aa007e9fa81d478e395677bd12ddccce5b272921a811f"],"state_sha256":"6595cab17a259d21163f49d7b3ebb0c884511a665fa51b3765786d133f67c969"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+50262/VQXct0MPdYEwfF9m/91aPrRwZo8/7z8THD5Lcao9FtNGG4qiPW8rFT7IDCmy3dFXheit0h7IdvPPFBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:17:35.558098Z","bundle_sha256":"2f536b07928606da82c6540d2d7bf1199cea78c43558933ba55b36737a0675cc"}}